Jiaoyang Huang

Jiaoyang Huang is an Associate Professor of Statistics and Data Science at the University of Pennsylvania's Department of Statistics and Data Science. His research interests include random matrix theory, random graphs, interacting particle systems, optimization of deep neural networks, posterior sampling, and uncertainty quantification of large scale inverse problems. He holds a secondary appointment in Mathematics. Huang's academic profile includes a Ph.D. in Mathematics from Harvard University and B.S. degrees in Mathematics and Computer Science and Technology from MIT and Tsinghua University, respectively. His work has been published in leading journals, and he has received several awards and honors.

Jiaoyang Huang is a researcher at the University of Pennsylvania, focusing on Probability theory, statistical learning, and mathematical physics. Their work explores the dynamics of deep neural networks, the role of information bottleneck in deep learning, and the convergence analysis of generative models. Huang also investigates random matrix theory, including bulk universality, eigenvalue statistics, and rigidity phenomena in sparse random matrices. Their research bridges theoretical probability with machine learning, emphasizing generalization and robustness in deep learning models. Additionally, Huang contributes to Bayesian inference and gradient flow methods in high-dimensional spaces.